![]() In the field of human factors, such problems have been repeatedly discussed (e.g., Bainbridge, 1983 Parasuraman and Riley, 1997). Disuse of new technology results in less innovation, while misuse of new technology can cause serious accidents. For sustainable industrial development in our society ( United Nations Industrial Development Organization, 2015 Fukuyama, 2018), it is important to understand how humans adapt to new technologies. When new technologies, not limited to automatic control of vehicles, are introduced, misuse (overreliance) and disuse (underutilization) of the technologies has often become a problem. For a while, it has been assumed that automatic control will be used with driver's monitoring to intervene immediately at any time if the automatic control fails to respond properly ( National Highway Traffic Safety Administration, 2016). However, there are still barriers to the full application of automatic driving (self-driving cars). In recent years, automatic control of steering has been actively developed due to the rapid progress of sensing and machine learning technologies. For cars, automation of some functions such as speed control (i.e., adaptive cruise control) and braking (anti-lock) have also been used for a long time. The operation of ships and aircraft has commonly been automated in our society. ![]() Although the application area of such technology is diverse, one of the recent prominent areas is the automatic operation of vehicles. This work shows how combining different paradigms of cognitive modeling can lead to practical representations and solutions to automation and trust in automation.Īutomation technology, which can partially substitute for human cognitive functions, has made remarkably progress recently. A run of this model simulated the overall trends of the behavioral data such as the performance (tracking accuracy), the auto use ratio, and the number of switches between the two modes, suggesting some validity of the assumptions made in our model. The utility values of these productions are updated based on rewards in every perception-action cycle. The model performs this task through productions that manage perception and motor control. We also introduce two methods of reinforcement learning: the summation of rewards over time and a gating mechanism. ![]() The model was developed by using a cognitive architecture, ACT-R (Adaptive Control of Thought-Rational). ![]() The paper uses a simple tracking task (which represents vehicle operation) to reveal how the reliance on automation changes as the success probabilities of the automatic and manual mode vary. This paper presents a cognitive model that simulates an adaptation process to automation in a time-critical task. 6College of Information Sciences and Technology, Pennsylvania State University, University Park, PA, United States.5Learning Technology Laboratory, Teikyo University, Tochigi, Japan.4Department of Information and Computer Sciences, Faculty of Humanity-Oriented Science and Engineering, Kinki University, Fukuoka, Japan.3Center for Research and Development in Admissions, Shizuoka University, Shizuoka, Japan.2Department of Cognitive and Psychological Sciences, Graduate School of Informatics, Nagoya University, Nagoya, Japan.1Department of Behavior Informatics, Faculty of Informatics, Shizuoka University, Hamamatsu, Japan.Junya Morita 1 * Kazuhisa Miwa 2 Akihiro Maehigashi 3 Hitoshi Terai 4 Kazuaki Kojima 5 Frank E.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |